dm-unstripe

index 83b9362be09c..e1c48a7f98f1 100644
@@ -269,6 +269,16 @@ config DM_BIO_PRISON
 
 source "drivers/md/persistent-data/Kconfig"
 
+config DM_UN_STRIPE
+       tristate "Transpose IO to individual drives on a raid device"
+       depends on BLK_DEV_DM
+       ---help---
+	  Enable this feature if you with to unstripe I/O on a RAID 0
+	  device to the respective drive. If your hardware has physical
+	  RAID 0 this module can unstripe the I/O to respective sides.
+
+	  If unsure say N.
+
 config DM_CRYPT
 	tristate "Crypt target support"
 	depends on BLK_DEV_DM

index f701bb211783..2cc380b71319 100644
@@ -43,6 +43,7 @@ obj-$(CONFIG_BCACHE)		+= bcache/
 obj-$(CONFIG_BLK_DEV_MD)	+= md-mod.o
 obj-$(CONFIG_BLK_DEV_DM)	+= dm-mod.o
 obj-$(CONFIG_BLK_DEV_DM_BUILTIN) += dm-builtin.o
+obj-$(CONFIG_DM_UN_STRIPE)   += dm-unstripe.o
 obj-$(CONFIG_DM_BUFIO)		+= dm-bufio.o
 obj-$(CONFIG_DM_BIO_PRISON)	+= dm-bio-prison.o
 obj-$(CONFIG_DM_CRYPT)		+= dm-crypt.o

new file mode 100644
index 000000000000..9c13e9316d52
@@ -0,0 +1,130 @@
+Device-Mapper Unstripe
+=====================
+
+The device-mapper unstripe (dm-unstripe) target provides a transparent
+mechanism to unstripe a device-mapper "striped" target to access the
+underlying disks without having to touch the true backing block-device.
+It can also be used to unstripe a hardware RAID-0 to access backing disks
+as well.
+
+
+Parameters:
+<drive (ex: /dev/nvme0n1)> <drive #> <# of drives> <chunk sectors>
+
+
+<drive>
+	The block device you wish to unstripe.
+
+<drive #>
+        The physical drive you wish to expose via this "virtual" device
+	mapper target. This must be 0 indexed.
+
+<# of drives>
+        The number of drives in the RAID 0.
+
+<chunk sectors>
+	The amount of 512B sectors in the chunk striping, or zero, if you
+	wish you use max_hw_sector_size.
+
+
+Why use this module?
+=====================
+
+    An example of undoing an existing dm-stripe:
+
+    This small bash script will setup 4 loop devices and use the existing
+    dm-stripe target to combine the 4 devices into one. It then will use
+    the unstripe target on the new combined stripe device to access the
+    individual backing loop devices. We write data to the newly exposed
+    unstriped devices and verify the data written matches the correct
+    underlying device on the striped array.
+
+    #!/bin/bash
+
+    MEMBER_SIZE=$((128 * 1024 * 1024))
+    NUM=4
+    SEQ_END=$((${NUM}-1))
+    CHUNK=256
+    BS=4096
+
+    RAID_SIZE=$((${MEMBER_SIZE}*${NUM}/512))
+    DM_PARMS="0 ${RAID_SIZE} striped ${NUM} ${CHUNK}"
+    COUNT=$((${MEMBER_SIZE} / ${BS}))
+
+    for i in $(seq 0 ${SEQ_END}); do
+      dd if=/dev/zero of=member-${i} bs=${MEMBER_SIZE} count=1 oflag=direct
+      losetup /dev/loop${i} member-${i}
+      DM_PARMS+=" /dev/loop${i} 0"
+    done
+
+    echo $DM_PARMS | dmsetup create raid0
+    for i in $(seq 0 ${SEQ_END}); do
+      echo "0 1 unstripe /dev/mapper/raid0 ${i} ${NUM} ${CHUNK}" | dmsetup create set-${i}
+    done;
+
+    for i in $(seq 0 ${SEQ_END}); do
+      dd if=/dev/urandom of=/dev/mapper/set-${i} bs=${BS} count=${COUNT} oflag=direct
+      diff /dev/mapper/set-${i} member-${i}
+    done;
+
+    for i in $(seq 0 ${SEQ_END}); do
+      dmsetup remove set-${i}
+    done
+
+    dmsetup remove raid0
+
+    for i in $(seq 0 ${SEQ_END}); do
+      losetup -d /dev/loop${i}
+      rm -f member-${i}
+    done
+
+==============
+
+
+    Another example:
+
+    Intel NVMe drives contain two cores on the physical device.
+    Each core of the drive has segregated access to its LBA range.
+    The current LBA model has a RAID 0 128k chunk on each core, resulting
+    in a 256k stripe across the two cores:
+
+       Core 0:                Core 1:
+      __________            __________
+      | LBA 512|            | LBA 768|
+      | LBA 0  |            | LBA 256|
+      ----------	    ----------
+
+    The purpose of this unstriping is to provide better QoS in noisy
+    neighbor environments. When two partitions are created on the
+    aggregate drive without this unstriping, reads on one partition
+    can affect writes on another partition. This is because the partitions
+    are striped across the two cores. When we unstripe this hardware RAID 0
+    and make partitions on each new exposed device the two partitions are now
+    physically separated.
+
+    With the module we were able to segregate a fio script that has read and
+    write jobs that are independent of each other. Compared to when we run
+    the test on a combined drive with partitions, we were able to get a 92%
+    reduction read latency using this device mapper target.
+
+
+====================
+Example scripts:
+
+
+dmsetup create nvmset1 --table '0 1 unstripe /dev/nvme0n1 1 2 0'
+dmsetup create nvmset0 --table '0 1 unstripe /dev/nvme0n1 0 2 0'
+
+There will now be two mappers:
+/dev/mapper/nvmset1
+/dev/mapper/nvmset0
+
+that will expose core 0 and core 1.
+
+
+# In a dm-stripe with 4 drives of chunk size 128K:
+dmsetup create raid_disk0 --table '0 1 unstripe /dev/mapper/striped 0 4 256'
+dmsetup create raid_disk1 --table '0 1 unstripe /dev/mapper/striped 1 4 256'
+dmsetup create raid_disk2 --table '0 1 unstripe /dev/mapper/striped 2 4 256'
+dmsetup create raid_disk3 --table '0 1 unstripe /dev/mapper/striped 3 4 256'
+